NVIDIA hat Qwen3.5-397B-A17B-NVFP4 V2 auf Hugging Face veröffentlicht. Die quantisierte Version ist für Text-, Bild- und Videoeingaben gedacht, hat Apache-2.0-Lizenz und nutzt SGLang für Inference.https://huggingface.co/nvidia/Qwen3.5-397B-A17B-NVFP4-V2#KI #AI #LLM #AISyndicate
Related
Security engineer ports password cracker hashcat to Gameboy Advance — 16.8 MHz chip can perform a meager 727 hashes a se...
Security engineer ports password cracker hashcat to Gameboy Advance — 16.8 MHz chip can perform a meager 727 hashes a second, 30 million times slower than a modern rigGameboy Advan...
Hunting a GExperts Code Librarian corruption bug with a custom debug memory managerAI;DR – This blog post and the debug ...
Hunting a GExperts Code Librarian corruption bug with a custom debug memory managerAI;DR – This blog post and the debug memory manager it describes were developed with significant ...
🤖 AI for designers and programmers 😂I find it absolutely hilarious that designers and programmers are completely split o...
🤖 AI for designers and programmers 😂I find it absolutely hilarious that designers and programmers are completely split on AI. Designers hate it(more or less) cause it's tied to per...